© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 17568
    Prev
    Next
    INDEX
    Explanations

    terms related to structural relationships and dependencies, particularly in contexts involving organization and categorization

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     myself
    -0.35
     Yourself
    -0.32
     ourselves
    -0.29
     yourself
    -0.27
     oneself
    -0.21
     yourselves
    -0.19
     Ñģебе
    -0.18
    ruba
    -0.16
    ufe
    -0.16
    tÃŃ
    -0.15
    POSITIVE LOGITS
     itself
    0.69
     proper
    0.46
    æľ¬
    0.43
    it
    0.41
     IT
    0.40
    IT
    0.36
    proper
    0.35
     æľ¬
    0.34
     Proper
    0.33
    ITS
    0.31
    Activations Density 0.063%

    No Known Activations